Back to GalleryBack
Model Comparison
Model Comparison
Compare performance, benchmarks, and characteristics
deepseek-v3.1-base
openrouter
Context163840 tokens
Input Price$0.2 / 1M tokens
Output Price$0.8 / 1M tokens
Loading comparison...
Model Comparison
| Metric |  |  |
|---|---|---|
Pricing | ||
| Input Price | $0.2 / 1M tokens | $3 / 1M tokens |
| Output Price | $0.8 / 1M tokens | $15 / 1M tokens |
Capabilities | ||
| Context Window | 163840 tokens | 256K tokens |
| Capabilities | tools | |
| Input type | text | text |
Category Scores | ||
| Overall Average | 46.5 | 71.3 |
| Academia | 45.3 | 76.4 |
| Finance | 45.1 | 81.0 |
| Marketing | 49.4 | 51.5 |
| Maths | 57.0 | 96.7 |
| Programming | 35.6 | 63.8 |
| Science | 57.4 | 87.6 |
| Writing | 35.9 | 42.2 |
Benchmark Tests | ||
| AIME | 25.3 | 94.3 |
| AA Coding Index | 35.6 | 63.8 |
| AAII | 33.2 | 65.3 |
| AA Math Index | 57.0 | 96.7 |
| DROP | 91.6 | _ |
| GPQA | 57.4 | 87.6 |
| HLE | 3.6 | 23.9 |
| LiveCodeBench | 35.9 | 81.9 |
| MATH-500 | 88.7 | 99.0 |
| MMLU | 88.5 | _ |
| MMLU-Pro | 75.6 | 86.6 |
| SciCode | 35.4 | 45.7 |
deepseek-v3.1-base Advantages
- • Lower input token cost ($0.2 / 1M tokens vs $3 / 1M tokens)
grok-4 Advantages
- • Higher benchmark scores (71.3 vs 46.5)
- • Larger context window (256K tokens vs 163840 tokens)